hooking-dev
commited on
Commit
•
a44127a
1
Parent(s):
72162b1
Upload 6 files
Browse files- config.json +5 -5
- model.safetensors +2 -2
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
config.json
CHANGED
@@ -13,12 +13,12 @@
|
|
13 |
"initializer_range": 0.02,
|
14 |
"layer_norm_epsilon": 1e-05,
|
15 |
"model_type": "gpt2",
|
16 |
-
"n_ctx":
|
17 |
-
"n_embd":
|
18 |
-
"n_head":
|
19 |
"n_inner": 1024,
|
20 |
-
"n_layer":
|
21 |
-
"n_positions":
|
22 |
"recompute_grad": true,
|
23 |
"reorder_and_upcast_attn": false,
|
24 |
"res_dropout": 0.1,
|
|
|
13 |
"initializer_range": 0.02,
|
14 |
"layer_norm_epsilon": 1e-05,
|
15 |
"model_type": "gpt2",
|
16 |
+
"n_ctx": 4096,
|
17 |
+
"n_embd": 1600,
|
18 |
+
"n_head": 25,
|
19 |
"n_inner": 1024,
|
20 |
+
"n_layer": 28,
|
21 |
+
"n_positions": 4096,
|
22 |
"recompute_grad": true,
|
23 |
"reorder_and_upcast_attn": false,
|
24 |
"res_dropout": 0.1,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1925c0de5426f54d69747941c887b17aa7970ea53827e9a2c0eff32c3ab8ff4c
|
3 |
+
size 1863516416
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,14 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
|
|
3 |
"eos_token": "</s>",
|
4 |
"mask_token": "<mask>",
|
5 |
"pad_token": "<pad>",
|
|
|
6 |
"unk_token": "<unk>"
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<sys>",
|
4 |
+
"<usr>",
|
5 |
+
"<asst>"
|
6 |
+
],
|
7 |
"bos_token": "<s>",
|
8 |
+
"cls_token": "<cls>",
|
9 |
"eos_token": "</s>",
|
10 |
"mask_token": "<mask>",
|
11 |
"pad_token": "<pad>",
|
12 |
+
"sep_token": "<sep>",
|
13 |
"unk_token": "<unk>"
|
14 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -55,14 +55,45 @@
|
|
55 |
"rstrip": false,
|
56 |
"single_word": false,
|
57 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
},
|
|
|
|
|
|
|
|
|
|
|
60 |
"bos_token": "<s>",
|
61 |
"clean_up_tokenization_spaces": true,
|
|
|
62 |
"eos_token": "</s>",
|
63 |
"mask_token": "<mask>",
|
64 |
"model_max_length": 1000000000000000019884624838656,
|
65 |
"pad_token": "<pad>",
|
|
|
66 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
67 |
"unk_token": "<unk>"
|
68 |
}
|
|
|
55 |
"rstrip": false,
|
56 |
"single_word": false,
|
57 |
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<sys>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<usr>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "<asst>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
}
|
83 |
},
|
84 |
+
"additional_special_tokens": [
|
85 |
+
"<sys>",
|
86 |
+
"<usr>",
|
87 |
+
"<asst>"
|
88 |
+
],
|
89 |
"bos_token": "<s>",
|
90 |
"clean_up_tokenization_spaces": true,
|
91 |
+
"cls_token": "<cls>",
|
92 |
"eos_token": "</s>",
|
93 |
"mask_token": "<mask>",
|
94 |
"model_max_length": 1000000000000000019884624838656,
|
95 |
"pad_token": "<pad>",
|
96 |
+
"sep_token": "<sep>",
|
97 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
98 |
"unk_token": "<unk>"
|
99 |
}
|